SOMICA - an application of self-organizing maps to geometric independent component analysis

Fabian J. Theis, Carlos García Puntonet, Elmar Wolfgang LangIJCNN 2003 · OpenReview

Abstract

Guided by the principles of geometric independent component analysis (ICA), we present a new approach (SOM-ICA) to linear geometric ICA using self-organizing map (SOM). We observe a considerable improvement in separation quality of different distributions, albeit at high computational costs. The SOMICA algorithm is therefore primarily interesting from a theoretical point of view bringing together ICA and SOMs; this intersection could lead to new proofs in geometric ICA based on similar theorems in the SOM theory.
BibTeX
@inproceedings{theis2003somica,
  author = {Fabian J. Theis and Carlos García Puntonet and Elmar Wolfgang Lang},
  title = {{SOMICA - an application of self-organizing maps to geometric independent component analysis}},
  booktitle = {IJCNN},
  year = {2003},
  url = {https://openreview.net/forum?id=Lea1Nbv3kt},
}

Loading related content...

Figure